© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 940
    Prev
    Next
    INDEX
    Explanations

    terms related to influence and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "influence" and related terms

    np_acts-logits-general · gemini-2.0-flash

    influence functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.77
     Dumas
    -0.73
     sacré
    -0.63
    チール
    -0.62
     ORAL
    -0.61
     câncer
    -0.61
    ly
    -0.59
     Peralta
    -0.59
     Dede
    -0.58
     Schritte
    -0.57
    POSITIVE LOGITS
    Influ
    1.02
     Influ
    0.95
     influences
    0.93
    influ
    0.93
     influencing
    0.92
     influenced
    0.90
     influence
    0.88
     influ
    0.87
    influenced
    0.86
    Influence
    0.85
    Activations Density 0.144%

    No Known Activations